Use GetExtensionMime for extraction methods; minor fixes.

archivesunleashed · Aug 16, 2019 · 6ffb43c · 6ffb43c
1 parent 9b3a845
commit 6ffb43c
Show file tree

Hide file tree

Showing 3 changed files with 277 additions and 33 deletions.
diff --git a/pom.xml b/pom.xml
@@ -655,9 +655,10 @@
       <!-- see issue #302
       <groupId>org.apache.tika</groupId>
       -->
-      <groupId>com.github.jrwiebe.tika</groupId>
+      <groupId>com.github.archivesunleashed.tika</groupId>
       <artifactId>tika-parsers</artifactId>
       <version>${tika.version}</version>
+      <classifier>shady</classifier>
       <exclusions>
         <exclusion>
           <groupId>com.fasterxml.jackson.core</groupId>

diff --git a/src/main/scala/io/archivesunleashed/matchbox/GetExtensionMime.scala b/src/main/scala/io/archivesunleashed/matchbox/GetExtensionMime.scala
@@ -40,7 +40,7 @@ object GetExtensionMime {
       if (urlExt != null && !urlExt.isEmpty) {
         // Reconcile Tika list and FilenameUtils extension
         if (tikaExtensions.size > 1) {
-          if (tikaExtensions.contains(urlExt)) {
+          if (tikaExtensions.contains("." + urlExt)) {
             ext = urlExt
           } else {
             ext = tikaExtensions(0).substring(1)